{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RERIF5PUKTIRYXX33FSDAJUJUZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"107cd53d82aec5f7cceacd6b5cea96257dcb4feb6482af2a164a2f9224c856b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T09:21:48Z","title_canon_sha256":"17b33fa76686c6e8e925d947949be18b360f7768569129f5b3ffbdb0da5d5422"},"schema_version":"1.0","source":{"id":"2503.18478","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.18478","created_at":"2026-07-05T10:54:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.18478v2","created_at":"2026-07-05T10:54:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18478","created_at":"2026-07-05T10:54:45Z"},{"alias_kind":"pith_short_12","alias_value":"RERIF5PUKTIR","created_at":"2026-07-05T10:54:45Z"},{"alias_kind":"pith_short_16","alias_value":"RERIF5PUKTIRYXX3","created_at":"2026-07-05T10:54:45Z"},{"alias_kind":"pith_short_8","alias_value":"RERIF5PU","created_at":"2026-07-05T10:54:45Z"}],"graph_snapshots":[{"event_id":"sha256:643eba84312d2d89e239bf5fc379582ef927231a91165e377a903de1c9d30fa3","target":"graph","created_at":"2026-07-05T10:54:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.18478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite advanced token compression techniques, existing multimodal large language models (MLLMs) still struggle with hour-long video understanding. In this work, we propose Video-XL-Pro, an efficient method for extremely long video understanding, built upon Reconstructive Compression of Tokens (ReCoT), a learnable module that leverages self-supervised learning to generate comprehensive and compact video tokens. ReCoT introduces two key components: (i) Dynamic Token Synthesizer (DTS): DTS generates pseudo-video tokens from static image tokens by learning intra-token relationships, which are the","authors_text":"Ao Li, Bo Zhao, Xiangrui Liu, Yang Tian, Yan Shu, Zheng Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T09:21:48Z","title":"Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18478","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:daff3fe2907e7820b20e15e9dc641c9a2937cd3f010986087af8d579d1ecabae","target":"record","created_at":"2026-07-05T10:54:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"107cd53d82aec5f7cceacd6b5cea96257dcb4feb6482af2a164a2f9224c856b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T09:21:48Z","title_canon_sha256":"17b33fa76686c6e8e925d947949be18b360f7768569129f5b3ffbdb0da5d5422"},"schema_version":"1.0","source":{"id":"2503.18478","kind":"arxiv","version":2}},"canonical_sha256":"892282f5f454d11c5efbd964302689a65aa3d09b537410c7629e1795ae460479","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"892282f5f454d11c5efbd964302689a65aa3d09b537410c7629e1795ae460479","first_computed_at":"2026-07-05T10:54:45.076204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:45.076204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q/CejoMOpLoO5N0eMlwha4KELNkuOgVbM/q09cHEsAF09XNBnKGWK2iKmu7wjE/cuC8GNN9VJyGcGpv0HU1mDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:45.076710Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.18478","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:daff3fe2907e7820b20e15e9dc641c9a2937cd3f010986087af8d579d1ecabae","sha256:643eba84312d2d89e239bf5fc379582ef927231a91165e377a903de1c9d30fa3"],"state_sha256":"44fdfc39849c9e29455a2854202044be46c15ddb5122259bc1541f5280a4b05e"}